Leveraging Action Unit Derivatives for Early-Stage Parkinson's Disease Detection

Objective

Hypomimia is a symptom of Parkinson's disease (PD), involving a decrease in facial movements and a loss of emotional expressions on the face. The objective of this study is to identify hypomimia in individuals in the early stage of PD by analyzing facial action units (AUs).

Methods

Our study included video recordings from 109 PD subjects and 45 healthy control (HC) subjects with an average of two videos per person (294 videos in total). The participants were requested to perform rapid syllable repetitions. For the purpose of discriminating between normal facial muscle movements and those specific to PD subjects experiencing hypomimia, we calculate the derivatives of the AUs. We derive global features based on the AUs intensities and their derivatives, and utilize XGBoost and Random Forest to perform the classification between PD and HC.

Results

We achieve subject-level classification scores of up to 73.7% for balanced accuracy (BA) and an area under the curve (AUC) of 81.39% using XGBoost, and a BA of 79.1% and an AUC of 83.7% with Random Forest. These findings show potential in identifying hypomimia during the early phases of PD. Moreover, this research could facilitate the continuous monitoring of hypomimia beyond hospital settings, enabled by telemedicine.